Topic-based chinese message polarity classification system at SIGHAN8-Task2

Chun Liao, Chong Feng, Sen Yang, Heyan Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes the topic-based Chinese message polarity classification system submitted by LCYS-TEAM at SIGHAN8-Task2. The system mainly includes two parts: 1) a graph-based ranking model integrating local and global information is adopted to represent the classification ability of words towards different topics. In construction of graph model, a new weighting approach and a PMI-based random jumping probability selection method is proposed. 2) For sentimental features, word embedding is employed for acquiring expanded topical words and syntactic dependency is adopted for getting topic-related sentimental words. Experiment results demonstrate the effectiveness of our system.

Original languageEnglish
Title of host publicationProceedings of the 8th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2015 - co-located with 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, ACL IJCNLP 2015
EditorsLiang-Chih Yu, Zhifang Sui, Yue Zhang, Vincent Ng
PublisherAssociation for Computational Linguistics (ACL)
Pages158-163
Number of pages6
ISBN (Electronic)9781941643570
Publication statusPublished - 2015
Event8th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2015 - Beijing, China
Duration: 30 Jul 201531 Jul 2015

Publication series

NameProceedings of the 8th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2015 - co-located with 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, ACL IJCNLP 2015

Conference

Conference8th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2015
Country/TerritoryChina
CityBeijing
Period30/07/1531/07/15

Fingerprint

Dive into the research topics of 'Topic-based chinese message polarity classification system at SIGHAN8-Task2'. Together they form a unique fingerprint.

Cite this